feat: Add cloud LLM provider support with Anthropic, OpenAI, and OpenAI-compatible APIs

This major update integrates cloud-based LLM providers alongside existing local
options, providing flexibility in deployment and usage.

## New Features

### LLM Provider Infrastructure
- Created unified `LLMProvider` trait for consistent provider interface
- Implemented `LLMProviderFactory` for dynamic provider instantiation
- Added comprehensive provider characteristics and configuration types

### Cloud Provider Implementations
- **Anthropic Claude**: Full support for Claude 3.5 (Opus, Sonnet, Haiku)
  - 200K token context window
  - Automatic retry with exponential backoff
  - Feature-gated with `anthropic` flag

- **OpenAI**: Complete GPT-4o and GPT-4 Turbo support
  - 128K token context window
  - Organization ID support
  - Feature-gated with `openai-llm` flag

- **OpenAI-Compatible**: Generic support for any OpenAI-compatible endpoint
  - Works with LM Studio, vLLM, Ollama v1 API, etc.
  - Optional API key authentication
  - Feature-gated with `openai-compatible` flag

### Updated Existing Providers
- Refactored `QwenClient` to implement `LLMProvider` trait
- Maintained backward compatibility with existing code
- Enhanced with consistent error handling and metrics

### Interactive Setup Wizard
- Created `codegraph-setup` binary for guided configuration
- Interactive prompts for all provider types
- Supports both embedding and LLM provider selection
- Automatic configuration file generation at ~/.codegraph/config.toml

### Configuration Enhancements
- Extended `LLMConfig` with cloud provider fields:
  - `anthropic_api_key`, `openai_api_key`
  - `openai_compatible_url` for custom endpoints
  - `max_tokens`, `timeout_secs` for fine-tuning
- Updated `.codegraph.toml.example` with comprehensive examples
- Added environment variable support (ANTHROPIC_API_KEY, OPENAI_API_KEY)

### Documentation
- Created comprehensive `docs/CLOUD_PROVIDERS.md` guide
  - Provider comparison matrix
  - Setup instructions for each provider
  - Usage examples and code snippets
  - Troubleshooting guide
  - Security best practices
- Updated README.md with cloud provider quickstart
- Added provider-specific configuration examples

## Technical Details

### Architecture
- All cloud providers follow the same `LLMProvider` trait
- Async-first design with proper error propagation
- Configurable retry logic with exponential backoff
- Token usage tracking and metrics
- Streaming support (prepared for future implementation)

### Code Quality
- Feature flags for optional dependencies
- Comprehensive test coverage for factory and providers
- Type-safe configuration with serde
- Clear error messages for missing API keys

### Dependencies Added
- dialoguer: Interactive CLI prompts
- dirs: Cross-platform config directory detection
- Feature flags for optional cloud providers

## Migration Guide

Existing configurations continue to work without changes. To use cloud providers:

1. Enable desired features during build:
   ```bash
   cargo build --features anthropic,openai-llm,openai-compatible
   ```

2. Run setup wizard or manually configure in .codegraph.toml:
   ```toml
   [llm]
   enabled = true
   provider = "anthropic"  # or "openai", "openai-compatible"
   model = "claude-3-5-sonnet-20241022"
   anthropic_api_key = "sk-ant-..."
   ```

## Files Changed
- Core implementation: 5 new provider files in codegraph-ai
- Factory: New llm_factory.rs for provider instantiation
- Configuration: Updated config_manager.rs with cloud fields
- Setup wizard: New codegraph-setup binary
- Documentation: New CLOUD_PROVIDERS.md guide
- Examples: Updated .codegraph.toml.example

## Breaking Changes
None. All changes are backward compatible with existing configurations.

## Future Enhancements
- Streaming response support
- Function calling for supported providers
- Response caching layer
- Cost tracking and optimization
- Multi-provider fallback strategies

Author: claude

.codegraph.toml.example

@@ -42,29 +42,56 @@ batch_size = 64
 # Set to false for maximum speed if using an external agent
 enabled = false
 
-# LLM provider: "ollama" or "lmstudio"
-# "lmstudio" recommended for MLX + Flash Attention 2 (macOS)
+# LLM provider: "ollama", "lmstudio", "anthropic", "openai", or "openai-compatible"
+# - "lmstudio": Local LLMs via LM Studio (recommended for MLX + Flash Attention 2 on macOS)
+# - "ollama": Local LLMs via Ollama
+# - "anthropic": Anthropic Claude API (requires API key)
+# - "openai": OpenAI GPT API (requires API key)
+# - "openai-compatible": Any OpenAI-compatible API endpoint
 provider = "lmstudio"
 
 # LLM model identifier
-# For LM Studio: lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
+# For LM Studio: lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF
 # For Ollama: Model name (e.g., "qwen2.5-coder:14b", "codellama:13b")
-# Recommended: DeepSeek Coder v2 Lite Instruct Q4_K_M (superior performance)
+# For Anthropic: Model name (e.g., "claude-3-5-sonnet-20241022", "claude-3-5-haiku-20241022")
+# For OpenAI: Model name (e.g., "gpt-4o", "gpt-4o-mini", "gpt-4-turbo")
+# For OpenAI-compatible: Custom model name
+# Recommended: DeepSeek Coder v2 Lite Instruct Q4_K_M (local), or Claude 3.5 Sonnet (cloud)
 model = "lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF"
 
-# LM Studio URL (default port 1234)
+# LM Studio URL (only used if provider is "lmstudio")
 lmstudio_url = "http://localhost:1234"
 
-# Ollama URL
+# Ollama URL (only used if provider is "ollama")
 ollama_url = "http://localhost:11434"
 
+# OpenAI-compatible base URL (only used if provider is "openai-compatible")
+# Example: "http://localhost:1234/v1" for LM Studio OpenAI endpoint
+# openai_compatible_url = "http://localhost:1234/v1"
+
+# Anthropic API key (only used if provider is "anthropic")
+# Can also be set via ANTHROPIC_API_KEY environment variable
+# anthropic_api_key = "sk-ant-..."
+
+# OpenAI API key (only used if provider is "openai" or some "openai-compatible" endpoints)
+# Can also be set via OPENAI_API_KEY environment variable
+# openai_api_key = "sk-..."
+
 # Context window size (tokens)
 # DeepSeek Coder v2 Lite: 32768 tokens
+# Claude 3.5 Sonnet: 200000 tokens
+# GPT-4o: 128000 tokens
 context_window = 32000
 
-# Temperature for generation (0.0 = deterministic, 1.0 = creative)
+# Temperature for generation (0.0 = deterministic, 2.0 = very creative)
 temperature = 0.1
 
+# Maximum tokens to generate in responses
+max_tokens = 4096
+
+# Request timeout in seconds
+timeout_secs = 120
+
 # Insights mode: "context-only", "balanced", or "deep"
 # - context-only: Return context only (fastest, for agents)
 # - balanced: Process top 10 files with LLM (good speed/quality)

README.md

@@ -48,6 +48,51 @@ That is the entire end-to-end workflow. LM Studio now has a project-specific vec
 
 ---
 
+## Cloud Provider Support ☁️
+
+CodeGraph now supports both **local** and **cloud-based** LLM and embedding providers, giving you flexibility in deployment:
+
+### Supported Cloud Providers
+
+- **Anthropic Claude** - State-of-the-art code understanding with 200K context
+- **OpenAI GPT** - GPT-4o and other OpenAI models
+- **OpenAI-Compatible** - Any custom OpenAI-compatible endpoint
+
+### Quick Setup with Wizard
+
+The easiest way to configure cloud providers:
+
+```bash
+# Build and run the setup wizard
+cargo build --release --bin codegraph-setup --features all-cloud-providers
+./target/release/codegraph-setup
+```
+
+The interactive wizard will guide you through:
+1. Choosing your embedding provider (ONNX, Ollama, LM Studio, or OpenAI)
+2. Selecting your LLM provider (Ollama, LM Studio, Anthropic, OpenAI, or custom)
+3. Configuring API keys and models
+4. Setting advanced options
+
+### Manual Configuration
+
+Or configure manually in `.codegraph.toml`:
+
+```toml
+[llm]
+enabled = true
+provider = "anthropic"  # or "openai", "ollama", "lmstudio", "openai-compatible"
+model = "claude-3-5-sonnet-20241022"
+anthropic_api_key = "sk-ant-..."  # Or set ANTHROPIC_API_KEY env var
+context_window = 200000
+temperature = 0.1
+max_tokens = 4096
+```
+
+**For detailed provider setup, pricing, and comparisons, see [docs/CLOUD_PROVIDERS.md](docs/CLOUD_PROVIDERS.md).**
+
+---
+
 ## Everyday CLI
 
 | Command | Description |

crates/codegraph-ai/Cargo.toml

@@ -28,3 +28,10 @@ arc-swap = { workspace = true }
 num_cpus = { workspace = true }
 prometheus = { workspace = true }
 reqwest = { workspace = true }
+
+[features]
+default = []
+anthropic = []
+openai-llm = []
+openai-compatible = []
+all-cloud-providers = ["anthropic", "openai-llm", "openai-compatible"]